@inproceedings{ch-wang-etal-2025-browsing,
    title = "Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning",
    author = "CH-Wang, Sky  and
      Deshpande, Darshan Girish  and
      Muresan, Smaranda  and
      Kannappan, Anand  and
      Qian, Rebecca",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.406/",
    pages = "8317--8331",
    ISBN = "979-8-89176-251-0",
    abstract = "We introduce Browsing Lost Unformed Recollections, a tip-of-the-tongue known-item search and reasoning benchmark for general AI assistants. BLUR introduces a set of 573 real-world validated questions that demand searching and reasoning across multimodal and multilingual inputs, as well as proficient tool use, in order to excel on. Humans easily ace these questions (scoring on average 98{\%}), while the best-performing system scores around 56{\%}. To facilitate progress toward addressing this challenging and aspirational use case for general AI assistants, we release 350 questions through a public leaderboard, retain the answers to 250 of them, and have the rest as a private test set."
}